xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-26 12:24:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

[TPU][Test] Rollback PR-21550. (#21619)

Browse Source 
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
This commit is contained in:
QiliangCui 2025-07-25 13:22:01 -07:00 committed by GitHub
parent 5ac3168ee3
commit 7cfea0df39
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tests/v1/tpu/test_basic.py
View File

@ -59,7 +59,7 @@ def test_basic(
# actually test chunked prompt
max_num_batched_tokens=1024,
max_model_len=8192,
gpu_memory_utilization=0.95,
gpu_memory_utilization=0.7,
max_num_seqs=max_num_seqs,
tensor_parallel_size=tensor_parallel_size) as vllm_model:
vllm_outputs = vllm_model.generate_greedy(example_prompts,